CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

examples : support encoder-decoder models in the simple example (#16002)

Browse Source 
Signed-off-by: Jie Fu <jiefu@tencent.com>
This commit is contained in:
Jie Fu (傅杰)
2025-09-17 15:29:00 +08:00
committed by GitHub
parent 85286f3548
commit 1cbd80f8cf
1 changed files with 14 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
examples/simple/simple.cpp
View File

@@ -145,6 +145,20 @@ int main(int argc, char ** argv) {
llama_batch batch = llama_batch_get_one(prompt_tokens.data(), prompt_tokens.size());
if (llama_model_has_encoder(model)) {
if (llama_encode(ctx, batch)) {
fprintf(stderr, "%s : failed to eval\n", __func__);
return 1;
}
llama_token decoder_start_token_id = llama_model_decoder_start_token(model);
if (decoder_start_token_id == LLAMA_TOKEN_NULL) {
decoder_start_token_id = llama_vocab_bos(vocab);
}
batch = llama_batch_get_one(&decoder_start_token_id, 1);
}
// main loop
const auto t_main_start = ggml_time_us();